Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3633 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.9571. Min Act: -0.0001

Data Index: 527933 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.8157. Min Act: -0.0001

Data Index: 768236 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 3.1751. Min Range: -3.1751

Max Act: 3.1751. Min Act: -0.0001

Data Index: 971509 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.8676. Min Act: -0.0001

Data Index: 142110 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7370. Min Act: -0.0001

Data Index: 988433 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7715. Min Act: -0.0001

Data Index: 346355 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.9974. Min Act: -0.0001

Data Index: 1043295 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.5521. Min Act: -0.0001

Data Index: 836090 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.8052. Min Act: -0.0001

Data Index: 1186088 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7929. Min Act: -0.0001

Data Index: 299270 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7631. Min Act: -0.0001

Data Index: 520913 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6117. Min Act: -0.0001

Data Index: 36547 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7391. Min Act: -0.0001

Data Index: 862970 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.5902. Min Act: -0.0001

Data Index: 1166942 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.9556. Min Act: -0.0001

Data Index: 372349 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.7010. Min Act: -0.0001

Data Index: 1345334 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6710. Min Act: -0.0001

Data Index: 178506 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6625. Min Act: -0.0001

Data Index: 923972 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6755. Min Act: -0.0001

Data Index: 119383 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6475. Min Act: -0.0001

Data Index: 916059 (C4 (Web Text))

Max Activating Token Index: 285